Student Success & Engagement Predict Models are updated three times each year before the Fall, Spring, and Summer terms.
- Fall term models are updated in late July or early August
- Spring term models are updated in late November or early December
- Summer term models are updated in late April or early May
Each time a course completion model is retrained, it may include all the final grade data that has successfully imported from the SIS up to the most recent fully completed term.
Each time a persistence model is retrained, it may include all enrollment data from any terms up to those that completed 6 months before the training period.
When a new model is ready for an upcoming term, only data from the intended term and later are scored. This prevents any large changes to the risk levels of current term data during critical moments of outreach planning.
The widgets for Course Completion/Persistence/Retention Rates on the SS&E admin dashboard use the same source data however they are NOT updated by the Predict Models. Rather, the dashboard widgets update nightly and only use historical data.
For example:
- Predict Models used in Fall 2023 were updated in July 2023, so the course completion model includes imported final grade data up to the most recent completed academic term, which is Spring 2023, since the summer terms were still ongoing.
- However, the persistence model could only use data up to the Fall 2022 academic term, because the Spring 2023 (most recent completed) term ended less than six months prior to the model's retraining.
- When the Fall 2023 models were updated, Summer 2023 was still in session. That meant that Summer 2023 enrollment data still used the Summer 2023 model versions. Only Fall 2023 and any available Spring 2024 data would have been changed to utilize the updated Fall 2023 models.